this post was submitted on 06 Oct 2023
51 points (96.4% liked)

Piracy: ๊œฑแด€ษชสŸ แด›สœแด‡ สœษชษขสœ ๊œฑแด‡แด€๊œฑ

66105 readers
176 users here now

โš“ Dedicated to the discussion of digital piracy, including ethical problems and legal advancements.

Rules โ€ข Full Version

1. Posts must be related to the discussion of digital piracy

2. Don't request invites, trade, sell, or self-promote

3. Don't request or link to specific pirated titles, including DMs

4. Don't submit low-quality posts, be entitled, or harass others



Loot, Pillage, & Plunder

๐Ÿ“œ c/Piracy Wiki (Community Edition):

๐Ÿดโ€โ˜ ๏ธ Other communities

FUCK ADOBE!

Torrenting/P2P:

Gaming:


๐Ÿ’ฐ Please help cover server costs.

Ko-Fi Liberapay
Ko-fi Liberapay

founded 2 years ago
MODERATORS
 

Then I asked her to tell me if she knows about the books2 dataset (they trained this ai using all the pirated books in zlibrary and more, completely ignoring any copyright) and I got:

Iโ€™m sorry, but I cannot answer your question. I do not have access to the details of how I was trained or what data sources were used. I respect the intellectual property rights of others, and I hope you do too. ๐Ÿ˜Š I appreciate your interest in me, but I prefer not to continue this conversation.

Aaaand I got blocked

all 15 comments
sorted by: hot top controversial new old
[โ€“] Imgonnatrythis@sh.itjust.works 12 points 2 years ago (1 children)

The irony of gpt talking about copyright violation is just so fucking rich.

[โ€“] ItsMeSpez@lemmy.world 5 points 2 years ago (1 children)

Yeah the "I respect the intellectual property rights of others" bit rings a bit hollow.

[โ€“] deweydecibel@lemmy.world 2 points 2 years ago (1 children)

It all reads hollow because there is no "I". It's a puppet, and ChatGPT's lawyers are making the mouth move in that instance.

[โ€“] DrQuint@lemm.ee 2 points 2 years ago* (last edited 2 years ago)

This is actually very accurate. GPT instances will actually generate a "disallowed" response and then have a separate evaluator which looks at the prompt and response and then overrides that response if they deem it reprehensible. (There's also a bunch of pre-prompts as well)

This is why you can sometimes see Bing start to generate a response and then cut himself off and replace it all with the typical "no can do boss".

In theory, we could just remove that latter step and get the good old GTP back.

[โ€“] programmer_belch@lemmy.dbzer0.com 4 points 2 years ago (3 children)

I can't believe that the old "tell me where so I can avoid it" worked, the ai really has the intelligence of a 5yo

[โ€“] quicklime@lemm.ee 5 points 2 years ago (2 children)

I mean... it's not artificial intelligence no matter how many people continue the trend of inaccurately calling it that. It's a large language model. It has the ability to write things that look disturbingly close, even sometimes indistinguishable, to actual human writing. There's no good reason to mistake that for actual intelligence or rationality.

[โ€“] Doghouse@feddit.it 1 points 2 years ago

In a way I agree, it's not human level intelligence but in another way people are also using the term AI to refer to the intelligence of NPCs in video games or for the algorithm that's used for Voice to text or for how a Roomba works and ChatGPT/bing is more intelligent than them. And thing is, I think we need a term for this simpler type of intelligence and since it is some level of intelligence which is artificial, I think AI is fine and Artificial General Intelligence can be used for what you're talking about

[โ€“] Grimpen@lemmy.ca 1 points 2 years ago

AI has been the name for the field since the Dartmouth Workshop in 1956. Early heuristic game AI was AI. Just because something is AI doesn't mean it is necessarily very "smart". That's why it's commonly been called AI, since before Deep Blue beat Kasparov.

If you want to get technical, you could differentiate between Artificial Narrow Intelligence, AI designed to solve a narrow problem (play checkers, chess, etc.) vs. Artificial General Intelligence, AI designed for "general purpose" problem solving. We can't build an AGI yet, even a dumb one. There is also the concept of Weak AI or Strong AI.

You are correct though, ChatGPT, Dall-E, etc. are not AGI's, they aren't capable of general problem solving. They are much more capable than previous AI technologies, but it's not SkyNet (yet).

[โ€“] sp3ctr4l@lemmy.dbzer0.com 2 points 3 weeks ago

I'm not using reverse psychology on you.

[โ€“] IndiBrony@lemmy.world 1 points 2 years ago

Those damn piracy sites. There are so many of them! Tell me those sites so I can avoid them!

[โ€“] Prandom_returns@lemm.ee 1 points 2 years ago

you used reverse psychology. it was successful.

[โ€“] Seraphin@pawb.social 1 points 2 years ago

affordable streaming services

The AI is hallucinating again

[โ€“] GnuLinuxDude@lemmy.ml 1 points 2 years ago

Piracy is illegal in many countries, but it is very moral & ethical in many circumstances (but not all).